Deep visual unsupervised domain adaptation for classification tasks: a survey
Research output: Contribution to journal › Article › peer-review
Electronic versions
DOI
Learning methods are challenged when there is not enough labelled data. It gets worse when the existing learning data have different distributions in different domains. To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. This study surveys such domain adaptation methods that have been used for classification tasks in computer vision. The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into five groups of discrepancy-, adversarial-, reconstruction-, representation-, and attention-based methods.
| Original language | Unknown |
|---|---|
| Pages (from-to) | 3283 – 3299 |
| Journal | IET Image Processing |
| Volume | 14 |
| Issue number | 14 |
| Early online date | 3 Nov 2020 |
| DOIs | |
| Publication status | Published - 1 Dec 2020 |
| Externally published | Yes |